MoonshotAI: Kimi K2 Thinking
Compare every TrustedRouter route for MoonshotAI: Kimi K2 Thinking, including token pricing, context limits, privacy policy, regional availability, measured uptime, and API support.
moonshotai/kimi-k2-thinking
| Publisher | Kimikimi |
|---|---|
| AI IQ | IQ 94 #87 on AI IQ |
| Context | 262,144 tokens |
| Providers | |
| Endpoints | 3 endpoints |
| Modes | chat open weights US providers |
| Routes | prepaid BYOK |
Current route evidence
Live leaderboardRecent provider-route uptime spans not enough data across 3 routes and 2 providers. Price comes from the current prepaid catalog. Speed and uptime come from routed probes rather than vendor claims.
Providers serving this model
Sorted by lowest combined prompt and completion price. Use
"provider": {"sort": "throughput"} in the request body
(or append :nitro to the model id) to route to the
fastest provider instead.
Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture.
| Provider | Usage | Prompt | Completion | TR router attested | Provider policy |
|---|---|---|---|---|---|
| GMI Cloudgmi | BYOK | $0.84/1M | $1.26/1M | yes | privacy unknown |
| Novita AInovita | Credits | $0.63/1M | $2.625/1M | yes | privacy unknown |
| Novita AInovita | BYOK | $0.63/1M | $2.625/1M | yes | privacy unknown |
Endpoint JSON: https://api.trustedrouter.com/v1/models/moonshotai/kimi-k2-thinking/endpoints
Compare MoonshotAI: Kimi K2 Thinking
All comparisons- DeepSeek: DeepSeek V4 Flash 0423 vs MoonshotAI: Kimi K2 Thinking32 combined provider routes